llama-3.1-nemotron-ultra-253b-v1
48±0
47interval49
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,318
- Last sync
- 3 min3 minutes ago
All sources syncing normally
- Arena · Text· 3 minutes ago
- Arena · WebDev· 3 minutes ago
- Arena · Vision· 3 minutes ago
- Arena · Agent· 3 minutes ago
- GPQA Diamond· 41 minutes ago
- SWE-bench· 41 minutes ago
- Terminal-Bench· 41 minutes ago
- ARC-AGI-2· 41 minutes ago
Filter by org:
Released:
One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.
| Model | Org | Interval | Swing | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | i | Add to compare | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 482 | llama-3.1-nemotron-ultra-253b-v1 | nvidia | Apr 2025 | — | 48.3 47.3Ranked 48.3 = (5 × 47.3 + 3 × 50) ÷ 8. 47.3 is the mean percentile over the 5 of 22 selected axes this model is measured on; fewer axes means a stronger pull toward 50. | 47–49 | 79 | 5/22 | #176–482 | 49 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 2 | — | — | 81 | 68 | 36 | — |
Blend is coverage-shrunk; the raw composite is shown greyed beside it · A low badge means fewer than 3 boards scored this model